Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2506.05171 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917390413987840 |
|---|---|
| author | He, Linxuan Fan, Lingxiang Jia, Qing-Shan Li, Ang Sang, Hongyan Wang, Ling Wen, Guanghui Lu, Jiwen Zhang, Tao Zhou, Jie Zhang, Yi Wang, Yisen Wei, Peng Wang, Zhongyuan Liu, Henry X. Feng, Shuo |
| author_facet | He, Linxuan Fan, Lingxiang Jia, Qing-Shan Li, Ang Sang, Hongyan Wang, Ling Wen, Guanghui Lu, Jiwen Zhang, Tao Zhou, Jie Zhang, Yi Wang, Yisen Wei, Peng Wang, Zhongyuan Liu, Henry X. Feng, Shuo |
| contents | Embodied AI systems, comprising AI models and physical plants, are increasingly prevalent across various applications. Due to the rarity of system failures, ensuring their safety in complex operating environments remains a major challenge, which severely hinders their large-scale deployment in safety-critical domains, such as autonomous vehicles, medical devices, and robotics. While achieving provable deterministic safety-verifying system safety across all possible scenarios-remains theoretically ideal, the rarity and complexity of corner cases make this approach impractical for scalable embodied AI systems. Instead, empirical safety evaluation is employed as an alternative, but the absence of provable guarantees imposes significant limitations. To address these issues, we argue for a paradigm shift to provable probabilistic safety that integrates provable guarantees with progressive achievement toward a probabilistic safety boundary on overall system performance. The new paradigm better leverages statistical methods to enhance feasibility and scalability, and a well-defined probabilistic safety boundary enables embodied AI systems to be deployed at scale. In this Perspective, we outline a roadmap for provable probabilistic safety, along with corresponding challenges and potential solutions. By bridging the gap between theoretical safety assurance and practical deployment, this Perspective offers a pathway toward safer, large-scale adoption of embodied AI systems in safety-critical applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_05171 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards provable probabilistic safety for scalable embodied AI systems He, Linxuan Fan, Lingxiang Jia, Qing-Shan Li, Ang Sang, Hongyan Wang, Ling Wen, Guanghui Lu, Jiwen Zhang, Tao Zhou, Jie Zhang, Yi Wang, Yisen Wei, Peng Wang, Zhongyuan Liu, Henry X. Feng, Shuo Systems and Control Artificial Intelligence Embodied AI systems, comprising AI models and physical plants, are increasingly prevalent across various applications. Due to the rarity of system failures, ensuring their safety in complex operating environments remains a major challenge, which severely hinders their large-scale deployment in safety-critical domains, such as autonomous vehicles, medical devices, and robotics. While achieving provable deterministic safety-verifying system safety across all possible scenarios-remains theoretically ideal, the rarity and complexity of corner cases make this approach impractical for scalable embodied AI systems. Instead, empirical safety evaluation is employed as an alternative, but the absence of provable guarantees imposes significant limitations. To address these issues, we argue for a paradigm shift to provable probabilistic safety that integrates provable guarantees with progressive achievement toward a probabilistic safety boundary on overall system performance. The new paradigm better leverages statistical methods to enhance feasibility and scalability, and a well-defined probabilistic safety boundary enables embodied AI systems to be deployed at scale. In this Perspective, we outline a roadmap for provable probabilistic safety, along with corresponding challenges and potential solutions. By bridging the gap between theoretical safety assurance and practical deployment, this Perspective offers a pathway toward safer, large-scale adoption of embodied AI systems in safety-critical applications. |
| title | Towards provable probabilistic safety for scalable embodied AI systems |
| topic | Systems and Control Artificial Intelligence |
| url | https://arxiv.org/abs/2506.05171 |